Attention Is All You Need Python Packages

whisper-timestamped

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

yunchang

USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference

qwen

My personal implementation of the model from "Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities", they haven't released model code yet sooo...

sockeye

Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch

crabnet

Predict materials properties using only the composition information!

longnet

Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"

mambatransformer

Integrating Mamba/SSMs with Transformer for Enhanced Long Context and High-Quality Sequence Modeling

alr-transformer

Zeta implemantion of "Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers"

tiny-gptv

Simple Implementation of TinyGPTV in super simple Zeta lego blocks

nonlinear-transformer

An Implementation of an Transformer model that generates tokens non-linearly all at once like the heptapods from Arrival

mgqa

The open source implementation of the multi grouped query attention by the paper "GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints"

screenai

Implementation of the ScreenAI model from the paper: "A Vision-Language Model for UI and Infographics Understanding"

autort-swarms

Implementation of AutoRT: "AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents"

video-vit

Paper - Pytorch

liquidnet

Implementation of Liquid Nets in Pytorch

audio-flamingo

Implementation of the model "AudioFlamingo" from the paper: "Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities"

m2pt

Implementation of M2PT in PyTorch from the paper: "Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities"

mamba-former

Paper - Pytorch

mobilevlm

Implementation of the LDP module block in PyTorch and Zeta from the paper: "MobileVLM: A Fast, Strong and Open Vision Language Assistant for Mobile Devices"

cross-attn

The open source implementation of the cross attention mechanism from the paper: "JOINTLY TRAINING LARGE AUTOREGRESSIVE MULTIMODAL MODELS"

simple-transformer

A simple and modular implementation of the Transformer model in PyTorch

jamba

jamba - Pytorch

hlt-torch

Paper - Pytorch

kosmos2-torch

Kosmos - Pytorch